mlsanityData to 14 Oct 2026

AU-IQA: A Benchmark Dataset for Perceptual Quality Assessment of AI-Enhanced User-Generated Content

arXiv 2508.05016 ↗First posted 7 Aug 2025cs.CV eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

AI-based image enhancement techniques have been widely adopted in various visual applications, significantly improving the perceptual quality of user-generated content (UGC). However, the lack of specialized quality assessment models has become a significant limiting factor in this field, limiting user experience and hindering the advancement of enhancement methods. While perceptual quality assessment methods have shown strong performance on UGC and AIGC individually, their effectiveness on AI-enhanced UGC (AI-UGC) which blends features from both, remains largely unexplored. To address this gap, we construct AU-IQA, a benchmark dataset comprising 4,800 AI-UGC images produced by three representative enhancement types which include super-resolution, low-light enhancement, and denoising. On this dataset, we further evaluate a range of existing quality assessment models, including traditional IQA methods and large multimodal models. Finally, we provide a comprehensive analysis of how well current approaches perform in assessing the perceptual quality of AI-UGC. The access link to the AU-IQA is https://github.com/WNNGGU/AU-IQA-Dataset.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 53 references that are in the map. First posted on arXiv 7 Aug 2025.

Builds on

33 of 53 references.

References · 33

  1. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2023Qwen Technical Reportcited by 3,344
  4. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  5. 2021Restormer: Efficient Transformer for High-Resolution Image Restorationcited by 1,627
  6. 2016Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoisingcited by 1,358
  7. 2021Palette: Image-to-Image Diffusion Modelscited by 1,300
  8. 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,254
  9. 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,224
  10. 2021MUSIQ: Multi-scale Image Quality Transformercited by 1,081
  11. 2022Exploring CLIP for Assessing the Look and Feel of Imagescited by 991
  12. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 866
21 more
  1. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 503
  2. 2017NIMA: Neural Image Assessmentcited by 389
  3. 2019KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessmentcited by 355
  4. 2024Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wildcited by 286
  5. 2023Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspectivecited by 280
  6. 2023DiffBIR: Towards Blind Image Restoration with Generative Diffusion Priorcited by 257
  7. 2025Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distributioncited by 141
  8. 2023Refusion: Enabling Large-Size Realistic Image Restoration with Latent-Space Diffusion Modelscited by 86
  9. 2024Towards Open-ended Visual Quality Comparisoncited by 85
  10. 2024LightenDiffusion: Unsupervised Low-Light Image Enhancement with Latent-Retinex Diffusion Modelscited by 71
  11. 2024Zero-Reference Low-Light Enhancement via Physical Quadruple Priorscited by 58
  12. 2023Masked Image Training for Generalizable Deep Image Denoisingcited by 57
  13. 2023A Perceptual Quality Assessment Exploration for AIGC Imagescited by 55
  14. 2024GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrievalcited by 33
  15. 2025Q-Eval-100K: Evaluating Visual Quality and Alignment Level for Text-to-Vision Contentcited by 32
  16. 2024Quality Assessment in the Era of Large Models: A Surveycited by 26
  17. 2024ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correctioncited by 15
  18. 2023Light-VQA: A Multi-Dimensional Quality Assessment Model for Low-Light Video Enhancementcited by 12
  19. 2025VARFVV: View-Adaptive Real-Time Interactive Free-View Video Streaming with Edge Computingcited by 12
  20. 2024AttentionLut: Attention Fusion-based Canonical Polyadic LUT for Real-time Image Enhancementcited by 11
  21. 2024THQA: A Perceptual Quality Assessment Database for Talking Headscited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025ViDA-UGC: Detailed Image Quality Analysis via Visual Distortion Assessment for UGC Images
  2. 2025Towards Explainable Partial-AIGC Image Quality Assessment
  3. 2024UHD-IQA Benchmark Database: Pushing the Boundaries of Blind Photo Quality Assessment
  4. 2025Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model
  5. 2024UniQA: Unified Vision-Language Pre-training for Image Quality and Aesthetic Assessment
  6. 2025Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption
  7. 2024Enhancing Descriptive Image Quality Assessment with A Large-scale Multi-modal Dataset
  8. 2024AI-generated Image Quality Assessment in Visual Communication